Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “evaluation datasets”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Towards robust surrogate models: Benchmarking machine learning approaches to expediting phase field simulations of brittle fracture

Data-driven approaches have the potential to make modeling complex, nonlinear physical phenomena significantly more computationally tractable. For example, computational modeling of fracture is a core challenge where machine learning techniques have the potential to provide a much needed speedup that would enable progress in areas such as multi-scale modeling and uncertainty quantification. Currently, phase field modeling (PFM) of fracture is one such approach that offers a convenient variational formulation to model crack nucleation, branching and propagation. To date, machine learning techniques have shown promise in approximating PFM simulations. While standard fracture benchmarks represent realistic scenarios frequently observed in practice, they typically do not provide sufficiently challenging tests for data-driven methods. Here, to address this gap, we introduce a challenging dataset based on PFM simulations designed to benchmark and advance ML methods for fracture modeling. This dataset includes three energy decomposition methods, two boundary conditions, and 1000 random initial crack configurations for a total of 6000 simulations. Each sample contains 100 time steps capturing the temporal evolution of the crack field. Alongside this dataset, we also implement and evaluate Physics Informed Neural Networks (PINN), Fourier Neural Operators (FNO), and UNet models as baselines, and explore the impact of ensembling strategies on prediction accuracy. With this combination of our dataset and baseline models drawn from the literature we aim to provide a standardized and challenging benchmark for evaluating machine learning approaches to solid mechanics. Our results highlight both the promise and limitations of popular current models, and demonstrate the utility of this dataset as a testbed for advancing machine learning in fracture mechanics research.

Benchmark dataset↗
DOE OSTI2025

Model Residuals as Shields: A Two-Level Formulation to Defend Smart Grids From Poisoning Attacks

The advancement of smart grids presents both vast opportunities and heightened cybersecurity risks. Data-driven defense mechanisms, though designed as a shield against these threats, can fall prey to poisoning attacks. We delve into regression settings, underscoring the imperative to fortify defenses against a spectrum of poison ratios, notably those above 0.5—an issue scarcely addressed in prior studies. Recognizing the susceptibilities of smart grids and their manipulable sensors, we exploit the very intent of poisoning attacks, compromising model accuracy, as our defense mechanism. Our proposed two-level optimization framework discerns between poisoned and authentic data based on model residuals, outperforming or matching existing methods in 72% to 77% of precision and 75% to 80% of recalls across various poisoning attacks, poison ratios, and datasets. Once the authentic data are identified, the trained model is adaptable for a variety of applications. Comprehensive evaluations on different smart grid datasets, pitted against myriad poisoning schemes, validate our methodology’s edge over existing methods. Here, we also shed light on the implications of model misspecification originating from temporal auto-correlation, a common feature in Internet of Things and smart grid data.

Adversarial machine learning (ML)↗
DOE OSTI2023

zPerf: A Statistical Gray-Box Approach to Performance Modeling and Extrapolation for Scientific Lossy Compression

With the scaling up of simulation-based scientific discovery on high-performance computing systems, the disparity between compute and I/O has increased, forcing domain scientists to save only a small amount of simulation data to persistent storage. This can result in the loss of essential physics fields that are needed for data analysis. While error-bounded lossy compression has made tremendous progress in bridging the gap between compute and I/O, the lack of understanding of compression performance remains a key hurdle to its wide adoption. Here, in this work, we present zPerf, a statistical gray-box performance modeling approach for scientific lossy compression. Our contributions are threefold: 1) We develop zPerf to estimate the performance of lossy compression techniques, based on in-depth understanding and statistical modeling for data features and core compression metrics; 2) We demonstrate the in-detailed implementation of zPerf using two case studies, where we derive the performance modeling for SZ and ZFP, two leading lossy compressors; 3) We evaluate the effectiveness of zPerf on real-world datasets across various domains. Based on the evaluation, we demonstrate the efficacy of the zPerf performance model; 4) We further discuss three case studies where zPerf is applied to extrapolate the compression ratio of SZ and ZFP with alternative encoding schemes as well as ZFP with an alternative transform scheme. Through the case studies, we demonstrate the potential of zPerf for exploring the design space of lossy compression, which has hardly been studied in the literature.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Maps of growing season gross primary production and net ecosystem exchange for Council Road Mile Marker 71, Seward Peninsula, Alaska, [2017-2023]

This data archive is in support of the Next-Generation Ecosystem Experiments in the Arctic (NGEE Arctic) publication "Integrating Characteristic Arctic Vegetation in a Land Surface Model Improves Representation of Carbon Dynamics Across a Tundra Landscape", by Murphy et al. (2025a). Murphy et al. (2025a) evaluated whether incorporating observed Arctic vegetation heterogeneity into ELM, the land model of the Department of Energy’s Energy Exascale Earth System Model (E3SM), improved simulations of tundra carbon cycling. The associated model archive can be found at Murphy et al. (2025b). The study focused on the spatial patterns and net landscape-level growing season productivity and carbon uptake. As part of this evaluation, observationally derived maps of average growing season (June–August) net ecosystem exchange (NEE) and gross primary production (GPP) were developed for the same domain. These maps, which form the dataset described here, integrate eddy covariance flux tower, remote sensing, and vegetation community data to provide spatially explicit benchmarks for model evaluation. The maps provide spatially explicit estimates of average growing season NEE and GPP across 13 tundra vegetation communities within the study domain. By combining flux tower observations with Airborne Visible-Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) hyperspectral imagery and drone-based normalized difference vegetation index (NDVI), these maps capture the heterogeneity of carbon fluxes associated with different Arctic vegetation types. While they represent average seasonal conditions rather than interannual variability, the maps provide a unique dataset for evaluating model performance, comparing vegetation community contributions to landscape-scale carbon cycling, and supporting regional analyses of Arctic carbon dynamics. This data archive contains 5 m resolution maps of vegetation communities, vegetation community average growing season GPP, and vegetation community average growing season NEE (three *.tif files), a User’s Guide (*pdf file), and Table 1 of the User’s Guide displaying vegetation community coverage and average growing season NEE and GPP values (*.csv file).

Murphy, Bailey [ORNL] (ORCID:0000000203995221)↗
DOE OSTI2021

Distance‐based reconstruction of protein quaternary structures from inter‐chain contacts

Abstract Predicting the quaternary structure of protein complex is an important problem. Inter‐chain residue‐residue contact prediction can provide useful information to guide the ab initio reconstruction of quaternary structures. However, few methods have been developed to build quaternary structures from predicted inter‐chain contacts. Here, we develop the first method based on gradient descent optimization (GD) to build quaternary structures of protein dimers utilizing inter‐chain contacts as distance restraints. We evaluate GD on several datasets of homodimers and heterodimers using true/predicted contacts and monomer structures as input. GD consistently performs better than both simulated annealing and Markov Chain Monte Carlo simulation. Starting from an arbitrarily quaternary structure randomly initialized from the tertiary structures of protein chains and using true inter‐chain contacts as input, GD can reconstruct high‐quality structural models for homodimers and heterodimers with average TM‐score ranging from 0.92 to 0.99 and average interface root mean square distance from 0.72 Å to 1.64 Å. On a dataset of 115 homodimers, using predicted inter‐chain contacts as restraints, the average TM‐score of the structural models built by GD is 0.76. For 46% of the homodimers, high‐quality structural models with TM‐score ≥ 0.9 are reconstructed from predicted contacts. There is a strong correlation between the quality of the reconstructed models and the precision and recall of predicted contacts. Only a moderate precision or recall of inter‐chain contact prediction is needed to build good structural models for most homodimers. Moreover, GD improves the quality of quaternary structures predicted by AlphaFold2 on a Critical Assessment of Techniques for Protein Structure Prediction–Critical Assessments of Predictions of Interactions dataset.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Changes in the Regional Water Cycle and Their Impact on Societies

ABSTRACT Changes in “blue water”, which is the total supply of fresh water available for human extraction over land, are quite closely related to changes in runoff or equivalently precipitation minus evaporation, . This article examines how climate change‐driven recent past and future changes in the regional water cycle relate to blue water availability and changes in human blue water demand. Although at the largest scales theoretical and numerical model predictions are in broad agreement with observations, at continental scales and below models predict large ranges of possible future and runoff especially at the scale of individual river catchments and for shorter timescale subseasonal floods and droughts. Nevertheless, it is expected that the occurrence and severity of floods will increase and that of droughts may increase, possibly compounded by human‐driven non‐climatic changes such as changes in land use, dam water impoundment, irrigation and extraction of groundwater. Contemporary assessments predict that increases in 21st century human water extraction in many highly‐populated regions are unlikely to be sustainable given projections of future . To reduce uncertainty in future predictions, there is an urgent need to improve modeling of atmospheric, land surface and human processes and how these components are coupled. This should be supported by maintaining the observing network and expanding it to improve measurements of land surface, oceanic and atmospheric variables. This includes the development of satellite observations stable over multiple decades and suitable for building reanalysis datasets appropriate for model evaluation.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Collaborative Study for Certification of Trace Elements in Uranium Ore Concentrate CRMs UCLO-1, UCHI-1, and UPER-1

Trace impurity patterns are important nuclear forensic signatures in uranium ore concentrates (UOCs) and Certified Reference Materials (CRMs) are used to validate the analysis methods employed by end users. Herein, we discuss the certification campaign for three new UOC CRMs from the National Research Council Canada: UCLO-1 (https://doi.org/10.4224/crm.2020.uclo-1), UCHI-1 (https://doi.org/10.4224/crm.2020.uchi-1), and UPER-1 (https://doi.org/10.4224/crm.2020.uper-1). This study involved 15 laboratories from 10 countries, using sector-field and (triple) quadrupole inductively-coupled plasma mass spectrometry to analyze 64 trace element impurities. We discuss the importance of the acids used for sample digestion, difficulties analyzing in a high uranium matrix, and data combination and uncertainty evaluation for this large dataset.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2024

In-situ strain behavior and BISON simulations of Zircaloy cladding subjected to temperature cycling separate-effects tests in a steam environment

Understanding fuel system performance during anticipated transients without scram (ATWSs) in boiling water reactors (BWRs) is necessary for refining current and future safety limits. High-fidelity material models and simulations are fundamental to rigorous assessment of zirconium-based cladding performance. However, experimental thermomechanical data during simulated ATWSs to validate these modes are limited. To provide relevant in-situ data, Zircaloy-4 cladding was subjected to cyclic heating in a steam environment to simulate an out-of-pile BWR ATWS. Digital image correlation was used to capture the cladding strain behavior in-situ for comparison against simulations using the BISON finite element code. Conventional high-temperature models were compared using multiple schemes to gain a better understanding of the applicability of three BISON models to BWR ATWS: (1) the default combination of creep models in BISON, (2) the high-temperature Erbacher model alone, and (3) the low-temperature Limback-Andersson model alone. The cases run with the Limback-Andersson model alone produced the lowest root mean square error (RMSE). The lowest RMSE for the Limback-Andersson model alone was 0.659%, and the highest RMSE reported was 4.22%. A data gap within the model in the temperature regime of interest was also identified, and to account for this gap, the current model in BISON is linearly interpolated between two separate datasets. In conclusion, this evaluation highlights the need to either develop a new model or to improve the existing model to capture transient creep effects resulting from a cyclic temperature transient.

Anticipated transient without SCRAM↗
DOE OSTI2023

Determining circuit model parameters from operation data for PV system degradation analysis: $\mathrm{PVPRO}$

Physics-based circuit parameters like series and shunt resistance are essential to provide insights into the degradation status of photovoltaic (PV) arrays. However, calculating these parameters typically requires a full current-voltage characteristic (I-V curve), the acquisition of which involves specific measurement devices and costly methods. Thus, I-V curves of the PV system level are often not available. Here this paper proposes a methodology (PVPRO) to estimate these I-V curve parameters using only operation (string-level DC voltage and current) and weather data (irradiance and temperature). PVPRO first performs multi-stage data pre-processing to remove noisy data. Next, the time-series DC data are used to fit an equivalent circuit single-diode model (SDM) to estimate the circuit parameters by minimizing the differences between the measured and estimated values. In this way, the time evolutions of the SDM parameters are obtained. We evaluate PVPRO on synthetic datasets and find an excellent estimation of both SDM and the key I-V parameters (e.g., open-circuit voltage, short-circuit current, maximum power, etc.) with an average relative error of 0.55%. The performance, especially the extracted degradation rate of parameters, is robust to various measurement noises and the presence of faults. In addition, PVPRO is applied to a 271 kW PV field system. The relative error between the real and estimated operation voltage and current is less than 1%, suggesting that degradation trends are well captured. PVPRO represents a promising open-source tool to extract the time-series degradation trends of key PV parameters from routine operation data.

14 SOLAR ENERGY↗
DOE OSTI2024

Nonlinear encoding in diffractive information processing using linear optical materials

Nonlinear encoding of optical information can be achieved using various forms of data representation. Here, we analyze the performances of different nonlinear information encoding strategies that can be employed in diffractive optical processors based on linear materials and shed light on their utility and performance gaps compared to the state-of-the-art digital deep neural networks. For a comprehensive evaluation, we used different datasets to compare the statistical inference performance of simpler-to-implement nonlinear encoding strategies that involve, e.g., phase encoding, against data repetition-based nonlinear encoding strategies. We show that data repetition within a diffractive volume (e.g., through an optical cavity or cascaded introduction of the input data) causes the loss of the universal linear transformation capability of a diffractive optical processor. Therefore, data repetition-based diffractive blocks cannot provide optical analogs to fully connected or convolutional layers commonly employed in digital neural networks. However, they can still be effectively trained for specific inference tasks and achieve enhanced accuracy, benefiting from the nonlinear encoding of the input information. Our results also reveal that phase encoding of input information without data repetition provides a simpler nonlinear encoding strategy with comparable statistical inference accuracy to data repetition-based diffractive processors. Our analyses and conclusions would be of broad interest to explore the push-pull relationship between linear material-based diffractive optical systems and nonlinear encoding strategies in visual information processors.

42 ENGINEERING↗
DOE OSTI2020

Coupling physics in machine learning to predict properties of high-temperatures alloys

Abstract High-temperature alloy design requires a concurrent consideration of multiple mechanisms at different length scales. We propose a workflow that couples highly relevant physics into machine learning (ML) to predict properties of complex high-temperature alloys with an example of the 9–12 wt% Cr steels yield strength. We have incorporated synthetic alloy features that capture microstructure and phase transformations into the dataset. Identified high impact features that affect yield strength of 9Cr from correlation analysis agree well with the generally accepted strengthening mechanism. As a part of the verification process, the consistency of sub-datasets has been extensively evaluated with respect to temperature and then refined for the boundary conditions of trained ML models. The predicted yield strength of 9Cr steels using the ML models is in excellent agreement with experiments. The current approach introduces physically meaningful constraints in interrogating the trained ML models to predict properties of hypothetical alloys when applied to data-driven materials.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Machine learning pipeline for denoising low signal-to-noise ratio and out-of-distribution transmission electron microscopy datasets

High-resolution transmission electron microscopy (HRTEM) is crucial for observing material’s structural and morphological evolution at Angstrom scales, but the electron beam can alter these processes. Devices such as CMOS-based direct-electron detectors operating in electron-counting mode can be utilized to substantially reduce the electron dosage. However, the resulting images often lead to a low signal-to-noise ratio, which requires frame integration that sacrifices temporal resolution. Several machine learning (ML) models have been recently developed to successfully denoise HRTEM images. Yet, these models are often computationally expensive, and their inference speeds on GPUs are outpaced by the imaging speed of advanced detectors, precluding in situ analysis. Furthermore, the performance of these denoising models on datasets with imaging conditions that deviate from the training datasets has not been evaluated. To mitigate these gaps, we propose a new self-supervised ML denoising pipeline specifically designed for time-series HRTEM images. This pipeline integrates a blind-spot convolution neural network with pre-processing and post-processing steps, including drift correction and low-pass filtering. Results demonstrate that our model outperforms various other ML and non-ML denoising methods in noise reduction and contrast enhancement, leading to improved visual clarity of atomic features. Additionally, the model is drastically faster than U-Net-based ML models and demonstrates excellent out-of-distribution generalization. The model’s computational inference speed is in the order of milliseconds per image, rendering it suitable for application in in-situ HRTEM experiments.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Revised monthly energy generation estimates for 1,500 hydroelectric power plants in the United States

Abstract The U.S. Energy Information Administration (EIA) conducts a regular survey (form EIA-923) to collect annual and monthly net generation for more than ten thousand U.S. power plants. Approximately 90% of the ~1,500 hydroelectric plants included in this data release are surveyed at annual resolution only and thus lack actual observations of monthly generation. For each of these plants, EIA imputes monthly generation values using the combined monthly generating pattern of other hydropower plants within the corresponding census division. The imputation method neglects local hydrology and reservoir operations, rendering the monthly data unsuitable for various research applications. Here we present an alternative approach to disaggregate each unobserved plant’s reported annual generation using proxies of monthly generation—namely historical monthly reservoir releases and average river discharge rates recorded downstream of each dam. Evaluation of the new dataset demonstrates substantial and robust improvement over the current imputation method, particularly if reservoir release data are available. The new dataset—named RectifHyd—provides an alternative to EIA-923 for U.S. scale, plant-level, monthly hydropower net generation (2001–2020). RectifHyd may be used to support power system studies or analyze within-year hydropower generation behavior at various spatial scales.

13 HYDRO ENERGY↗
DOE OSTI2024

Question-answering system extracts information on injection drug use from clinical notes

Background. Injection drug use (IDU) can increase mortality and morbidity. Therefore, identifying IDU early and initiating harm reduction interventions can benefit individuals at risk. However, extracting IDU behaviors from patients’ electronic health records (EHR) is difficult because there is no other structured data available, such as International Classification of Disease (ICD) codes, and IDU is most often documented in unstructured free-text clinical notes. Although natural language processing can efficiently extract this information from unstructured data, there are no validated tools. Methods. Here, to address this gap in clinical information, we design a question-answering (QA) framework to extract information on IDU from clinical notes for use in clinical operations. Our framework involves two main steps: (1) generating a gold-standard QA dataset and (2) developing and testing the QA model. We use 2323 clinical notes of 1145 patients curated from the US Department of Veterans Affairs (VA) Corporate Data Warehouse to construct the gold-standard dataset for developing and evaluating the QA model. We also demonstrate the QA model’s ability to extract IDU-related information from temporally out-of-distribution data. Results. Here, we show that for a strict match between gold-standard and predicted answers, the QA model achieves a 51.65% F1 score. For a relaxed match between the gold-standard and predicted answers, the QA model obtains a 78.03% F1 score, along with 85.38% Precision and 79.02% Recall scores. Moreover, the QA model demonstrates consistent performance when subjected to temporally out-of-distribution data. Conclusions. Our study introduces a QA framework designed to extract IDU information from clinical notes, aiming to enhance the accurate and efficient detection of people who inject drugs, extract relevant information, and ultimately facilitate informed patient care.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Discriminative versus generative approaches to simulation-based inference

Most of the fundamental, emergent, and phenomenological parameters of particle and nuclear physics are determined through parametric template fits. Simulations are used to populate histograms which are then matched to data. This approach is inherently lossy, since histograms are binned and low-dimensional. Deep learning has enabled unbinned and high-dimensional parameter estimation through neural likelihood(-ratio) estimation. We compare two approaches for neural simulation-based inference (NSBI): one based on discriminative learning (classification) and one based on generative modeling. These two approaches are directly evaluated on the same datasets, with a similar level of hyperparameter optimization in both cases. In addition to a Gaussian dataset, we study NSBI using a Higgs boson dataset from the FAIR Universe Challenge. We find that both the direct likelihood and likelihood ratio estimation are able to effectively extract parameters with reasonable uncertainties. For the numerical examples and within the set of hyperparameters studied, we found that the likelihood ratio method is more accurate and/or precise. Both methods have a significant spread from the network training and would require ensembling or other mitigation strategies in practice.

high energy physics↗
DOE OSTI2024

Extraction of the neutron F 2 structure function from inclusive proton and deuteron deep-inelastic scattering data

The available world deep-inelastic scattering (DIS) data on proton and deuteron structure functions F 2 p , F 2 d , and their ratios are leveraged to extract the free neutron F 2 n structure function, the F 2 n / F 2 p ratio, and associated uncertainties using the latest nuclear effect calculations in the deuteron. Special attention is devoted to the normalization of the proton and deuteron experimental datasets and to the treatment of correlated systematic errors, as well as the quantification of procedural and theoretical uncertainties. The extracted F 2 n dataset is utilized to evaluate the Q 2 dependence of the Gottfried sum rule and the nonsinglet F 2 p − F 2 n moments. To facilitate replication of our study, as well as for general applications, we provide a comprehensive DIS database including all recent Jefferson Lab 6 GeV measurements, the extracted F n 2 , a modified CTEQ-JLab global parton distribution function fit named CJ15nlo_mod, and grids with calculated proton, neutron, and deuteron DIS structure functions. Published by the American Physical Society 2024

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

A Hybrid Anomaly Detection Approach for Obfuscated Malware

With the rapid evolution of malicious software, cyber threats have become increasingly sophisticated, employing advanced obfuscation techniques to evade traditional detection methods. This study presents a hybrid anomaly detection approach applied to obfuscated malware. Even though there is a large body of research in this field, existing malware detection techniques have some drawbacks, such as requiring large amounts of data, trustworthiness (imprecise results) of algorithms, and advanced obfuscation. To overcome these challenges, there is a need to employ solid and efficient techniques for malware detection. This paper proposes a hybrid approach, combining an autoencoder with traditional machine-learning methods to create an efficient malware detection framework. We used the malware memory dataset (MalMemAnalysis-2022) to evaluate this framework. The results indicate that our proposed approach can detect obfuscated malware when a deep autoencoder used for feature learning is combined with logistic regression, and it is extremely fast with an Accuracy, Detection Rate (DR), Matthew Correlation Coefficient(MCC), and Statistical Parity Difference

malware detection, Hybrid Anomly Detection, Obfusc↗
DOE OSTI2026

Optimal Client Sampling in Federated Learning with Client-level Heterogeneous Differential Privacy

Federated Learning with client-level differential privacy (DP) provides a promising framework for collaboratively training models while rigorously protecting clients’ privacy. However, classic approaches like DP-FedAvg struggle when clients have heterogeneous privacy requirements, as they must uniformly enforce the strictest privacy level across all clients, leading to excessive DP noise and significant degradation in model utility. Existing methods to improve the model utility in such heterogeneous privacy settings often assume a trusted server and are largely heuristic, resulting in suboptimal performance and lacking strong theoretical foundations. Here, in this work, we address these challenges under a practical attack model where both clients and the server are honest-but-curious. We propose GDPFed, which partitions clients into groups based on their privacy budgets and achieves client-level DP within each group to reduce the privacy budget waste and hence improve the model utility. Based on the privacy and convergence analysis of GDPFed, we find that the magnitude of DP noise depends on both model dimensionality and the per-group client sampling ratios. To further improve the performance of GDPFed, we introduce GDPFed+, which integrates model sparsification to eliminate unnecessary noise and optimizes per-group client sampling ratios to minimize convergence error. Extensive empirical evaluations on multiple benchmark datasets demonstrate the effectiveness of GDPFed+, showing substantial performance gains compared with state-of-the-art methods.

Xu, Jiahao [Univ. of Nevada, Reno, NV (United Stat↗